Skip to main content
Erschienen in:
Buchtitelbild

2019 | OriginalPaper | Buchkapitel

Foothill: A Quasiconvex Regularization for Edge Computing of Deep Neural Networks

verfasst von : Mouloud Belbahri, Eyyüb Sari, Sajad Darabi, Vahid Partovi Nia

Erschienen in: Image Analysis and Recognition

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Deep neural networks (DNNs) have demonstrated success for many supervised learning tasks, ranging from voice recognition, object detection, to image classification. However, their increasing complexity might yield poor generalization error that make them hard to be deployed on edge devices. Quantization is an effective approach to compress DNNs in order to meet these constraints. Using a quasiconvex base function in order to construct a binary quantizer helps training binary neural networks (BNNs) and adding noise to the input data or using a concrete regularization function helps to improve generalization error. Here we introduce foothill function, an infinitely differentiable quasiconvex function. This regularizer is flexible enough to deform towards \(L_1\) and \(L_2\) penalties. Foothill can be used as a binary quantizer, as a regularizer, or as a loss. In particular, we show this regularizer reduces the accuracy gap between BNNs and their full-precision counterpart for image classification on ImageNet.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Bishop, C.M.: Training with noise is equivalent to tikhonov regularization. Neural Comput. 7(1), 108–116 (1995)CrossRef Bishop, C.M.: Training with noise is equivalent to tikhonov regularization. Neural Comput. 7(1), 108–116 (1995)CrossRef
2.
Zurück zum Zitat Darabi, S., Belbahri, M., Courbariaux, M., Nia, V.P.: BNN+: improved binary network training. arXiv preprint arXiv:1812.11800 (2018) Darabi, S., Belbahri, M., Courbariaux, M., Nia, V.P.: BNN+: improved binary network training. arXiv preprint arXiv:​1812.​11800 (2018)
3.
Zurück zum Zitat Frank, L.E., Friedman, J.H.: A statistical view of some chemometrics regression tools. Technometrics 35(2), 109–135 (1993)CrossRef Frank, L.E., Friedman, J.H.: A statistical view of some chemometrics regression tools. Technometrics 35(2), 109–135 (1993)CrossRef
4.
Zurück zum Zitat Hoerl, A.E., Kennard, R.W.: Ridge regression: biased estimation for nonorthogonal problems. Technometrics 12(1), 55–67 (1970)CrossRef Hoerl, A.E., Kennard, R.W.: Ridge regression: biased estimation for nonorthogonal problems. Technometrics 12(1), 55–67 (1970)CrossRef
5.
Zurück zum Zitat Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks. In: Advances in Neural Information Processing Systems (2016) Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks. In: Advances in Neural Information Processing Systems (2016)
6.
7.
Zurück zum Zitat Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015) Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:​1502.​03167 (2015)
9.
Zurück zum Zitat Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012) Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
10.
Zurück zum Zitat Lin, X., Zhao, C., Pan, W.: Towards accurate binary convolutional neural network. In: Advances in Neural Information Processing Systems, pp. 345–353 (2017) Lin, X., Zhao, C., Pan, W.: Towards accurate binary convolutional neural network. In: Advances in Neural Information Processing Systems, pp. 345–353 (2017)
11.
Zurück zum Zitat Nia, V.P., Belbahri, M.: Binary quantizer. J. Comput. Vis. Imaging Syst. 4(1), 3 (2018) Nia, V.P., Belbahri, M.: Binary quantizer. J. Comput. Vis. Imaging Syst. 4(1), 3 (2018)
13.
Zurück zum Zitat Rifai, S., Glorot, X., Bengio, Y., Vincent, P.: Adding noise to the input of a model trained with a regularized objective. arXiv preprint arXiv:1104.3250 (2011) Rifai, S., Glorot, X., Bengio, Y., Vincent, P.: Adding noise to the input of a model trained with a regularized objective. arXiv preprint arXiv:​1104.​3250 (2011)
14.
Zurück zum Zitat Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014) Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:​1409.​1556 (2014)
15.
Zurück zum Zitat Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)MathSciNetMATH Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)MathSciNetMATH
16.
Zurück zum Zitat Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015) Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)
17.
Zurück zum Zitat Tang, W., Hua, G., Wang, L.: How to train a compact binary neural network with high accuracy? In: Thirty-First AAAI Conference on Artificial Intelligence (2017) Tang, W., Hua, G., Wang, L.: How to train a compact binary neural network with high accuracy? In: Thirty-First AAAI Conference on Artificial Intelligence (2017)
18.
Zurück zum Zitat Tibshirani, R.: Regression shrinkage and selection via the lasso. J. Roy. Stat. Soc. Series B 58, 267–288 (1996)MathSciNetMATH Tibshirani, R.: Regression shrinkage and selection via the lasso. J. Roy. Stat. Soc. Series B 58, 267–288 (1996)MathSciNetMATH
19.
Zurück zum Zitat Wager, S., Wang, S., Liang, P.S.: Dropout training as adaptive regularization. In: Advances in Neural Information Processing Systems, pp. 351–359 (2013) Wager, S., Wang, S., Liang, P.S.: Dropout training as adaptive regularization. In: Advances in Neural Information Processing Systems, pp. 351–359 (2013)
20.
Zurück zum Zitat Zou, H., Hastie, T.: Regularization and variable selection via the elastic net. J. Roy. Stat. Soc. Series B 67(2), 301–320 (2005)MathSciNetCrossRef Zou, H., Hastie, T.: Regularization and variable selection via the elastic net. J. Roy. Stat. Soc. Series B 67(2), 301–320 (2005)MathSciNetCrossRef
Metadaten
Titel
Foothill: A Quasiconvex Regularization for Edge Computing of Deep Neural Networks
verfasst von
Mouloud Belbahri
Eyyüb Sari
Sajad Darabi
Vahid Partovi Nia
Copyright-Jahr
2019
DOI
https://doi.org/10.1007/978-3-030-27272-2_1

Premium Partner